{"id":28795847,"url":"https://github.com/ukplab/germeval2017-sentiment-detection","last_synced_at":"2026-03-09T03:35:18.362Z","repository":{"id":37663727,"uuid":"102629756","full_name":"UKPLab/germeval2017-sentiment-detection","owner":"UKPLab","description":"Sentence Embeddings used in the GermEval-2017 Submission","archived":false,"fork":false,"pushed_at":"2023-05-23T00:12:36.000Z","size":167,"stargazers_count":13,"open_issues_count":3,"forks_count":1,"subscribers_count":22,"default_branch":"master","last_synced_at":"2025-07-05T03:12:36.096Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/UKPLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2017-09-06T16:03:15.000Z","updated_at":"2023-11-13T14:43:41.000Z","dependencies_parsed_at":"2025-06-18T03:11:26.710Z","dependency_job_id":"5a831a9a-9460-48df-ae80-bd2ef4d02c49","html_url":"https://github.com/UKPLab/germeval2017-sentiment-detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/UKPLab/germeval2017-sentiment-detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fgermeval2017-sentiment-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fgermeval2017-sentiment-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fgermeval2017-sentiment-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fgermeval2017-sentiment-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UKPLab","download_url":"https://codeload.github.com/UKPLab/germeval2017-sentiment-detection/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UKPLab%2Fgermeval2017-sentiment-detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30281584,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-09T02:57:19.223Z","status":"ssl_error","status_checked_at":"2026-03-09T02:56:26.373Z","response_time":61,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-18T03:10:30.183Z","updated_at":"2026-03-09T03:35:18.333Z","avatar_url":"https://github.com/UKPLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# UKP TU-DA at GermEval 2017: Deep Learning for Aspect Based Sentiment Detection\n## GermEval-2017 : Shared Task on Aspect-based Sentiment in Social Media Customer Feedback\n\nThis is the repository to our experiments for the [GermEval2017 shared task](https://sites.google.com/view/germeval2017-absa/home) reported in Lee et al., *[UKP TU-DA at GermEval 2017: Deep Learning for Aspect Based Sentiment Detection](https://duepublico.uni-duisburg-essen.de/servlets/DerivateServlet/Derivate-45683/GermEval2017_Proceedings.pdf)*.\n\n\nWe provide the German sentence embeddings trained with sent2vec using Wikipedia, Twitter, and the shared task data as well as information about how to use them. \n\nThe base code for the ensemble classifier we used in subtasks A and B can be found [here](https://github.com/UKPLab/semeval2017-scienceie). \n\nFor access to the multi-task learning framework we used for subtasks C and D, please contact us. Our implementation was based on [this](https://github.com/UKPLab/thesis2018-tk_mtl_sequence_tagging) TensorFlow framework.\n\n\nPlease use the following citation:\n\n```\n@inproceedings{Lee:2017,\n\ttitle = {UKP TU-DA at GermEval 2017: Deep Learning for Aspect Based Sentiment Detection},\n\tauthor = {Lee, Ji-Ung and Eger, Steffen and Daxenberger, Johannes and Gurevych, Iryna},\n\torganization = {German Society for Computational Linguistics},\n\tbooktitle = {Proceedings of the  GSCL GermEval Shared Task on Aspect-based Sentiment in Social Media Customer Feedback},\n\tpages = {22--29},\n\tmonth = sep,\n\tyear = {2017},\n\tlocation = {Berlin, Germany},\n}\n```\n\n\n\u003e **Abstract:** This paper describes our submissions to the GermEval 2017 Shared Task, which focused on the analysis of customer feedback about the Deutsche Bahn AG.\n\u003e We used sentence embeddings and an ensemble of classifiers for two sub-tasks as well as state-of-the-art sequence taggers for two other sub-tasks.\n\n\nContact persons:\n\n  * Ji-Ung Lee, lee@ukp.informatik.tu-darmstadt.de \n  * Steffen Eger, eger@ukp.informatik.tu-darmstadt.de\n  * Johannes Daxenberger, daxenberger@ukp.informatik.tu-darmstadt.de\n\n\nhttps://www.ukp.tu-darmstadt.de/\n\nhttps://www.tu-darmstadt.de/\n\n\nDon't hesitate to send us an e-mail or report an issue, if something is broken (and it shouldn't be) or if you have further questions.\n\n\u003e This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication. \n\n## MTL for Tasks C and D\n\nThe folder ```mtl-sequence-tagging-framework``` contains the code to run our experiments for tasks C and D (using multitask learning). Please follow the instructions in the [README.md](mtl-sequence-tagging-framework/README.md). We updated the code to be run with python 3.6 and Tensorflow 2.X.\n\n\n## Embeddings for Tasks A, B (and C)\n\nDue to a big file size the embeddings are not stored in this repository. You can find them here:\n\n* [Embeddings in different sizes](https://public.ukp.informatik.tu-darmstadt.de/GermEval2017_Embeddings/) \n* [Embeddings and data used for the submitted results](https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/2483)\n\nThe embeddings were trained on the [shared task data](https://sites.google.com/view/germeval2017-absa/data), [Wikipedia data](https://sites.google.com/site/rmyeid/projects/polyglot), and Tweets from the [German Sentiment Corpus](https://spinningbytes.com/resources/germansentiment/).\n\nEmbedding dimensions are 500, 700, and 1000, as specified in their names and were trained with the following parameters:\n-*minCount* 10\t-*epoch* 5\t-*lr* 0.2\t-*wordNgrams* 2\t-*loss* ns\t-*neg* 10\t-*thread* 5\t-*t* 0.0001\t-*dropoutK* 2\t-*bucket* 2000000\n\n\n## Requirements\n\n* [Sent2Vec](https://github.com/epfml/sent2vec)\n\n\n## Using the embeddings\n\nOn Linux you can unpack the embeddings with:\n\n```\n$tar --lzma -xvf ../path-to-model/model.bin.tar.lzma\n```\n\nFor obtaining sentence embeddings from the sent2vec models do:\n\n```\n$./fasttext print-sentence-vectors ../path-to-model/model.bin \u003c input-sentences.txt \u003e embedding-vectors.txt\n```\n\n## References\n\n### A Twitter Corpus and Benchmark Resources for German Sentiment Analysis. \nMark Cieliebak, Jan Deriu, Fatih Uzdilli, and Dominic Egger. In “Proceedings of the 4th International Workshop on Natural Language Processing for Social Media (SocialNLP 2017)”, Valencia, Spain, 2017\n\n### Polyglot: Distributed Word Representations for Multilingual NLP\nRami Al-Rfou, Bryan Perozzi, and Steven Skiena. In “Proceedings Seventeenth Conference on Computational Natural Language Learning (CoNLL 2013)”, Sofia, Bulgaria, 2013\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukplab%2Fgermeval2017-sentiment-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fukplab%2Fgermeval2017-sentiment-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukplab%2Fgermeval2017-sentiment-detection/lists"}